The simple humanity in this candid description brought a small tear to my eyes. I'd say that the classical approach to this is a dry, clinical description of a depression stage, or a description of a how and not a why. Very welcomed in the age of AI slop!

Now, an idea: HN is always complaining that an ipad (or any other tablet) is a consumption device, as it is not designed to be used with keyboard/mouse. Do any of you know if there is an app where you can write APL with a stylus, and has the ability to evaluate expression on the fly, similar to a repl? That would be an awesome thing to do.

I'm not against the considerations of the article regarding the user and its state of mind, but please do add as much technical detail as possible!

Even if an error message is a cryptic error code, that's better than a "Something went wrong" message. This is not better, or even friendlier, UX. An error code can be referenced, can be searched on the internet, can be passed around on a ticket or on a call... add parameters to your error template, reference the name of the file, the item name that does not respond, the HTTP error code... just give the user some transparency, some agency. Help the client build up a mental model of the error: when / how / why might it be happening.

You'd have to steer the LLM to use the style you want, and not massively overarchitect things though, but that's going to be an issue nonetheless.

Comments URL: https://news.ycombinator.com/item?id=48100449

Points: 2

# Comments: 0

The concept of an accent is broad, but at least part of it you need to learn together with the language, as speaking a non-native language with a thick accent is partly based on the fact that you have yet to learn.

Without being exhaustive, things that might fall into the "speaks with an accent" concept in this thread:

   - Prosody. Prosody can vary per region but a distinctly alien prosody to a language is a barrier for the receptor of the message, that expects a given language and a range of prosodies. E.g. as I know french quite well, hearing english with a heavy french accent makes my brain try to understand what's being said as said in french, and interferes a lot.

   - Sound shifts for particular phonemes. While some of it might be local to the language in certain registers (idea --> /ide"er"/, three --> /free/), others are clearly issues in the target language pronunciation (eg. japanese people having trouble with the l phoneme, spanish people adding an /e/ sound prior to an s-mobile, or v versus b for spanish people also).

   - Connected speech. Where do you end words, how do you omit sounds, etc. Also massive hindrance to understanding.

   - Grammar. Alien grammar is a hindrance to communication. You need to learn that.

  1. Even if the task is unreasonable, it is good to showcase that the LLM will perform poorly - warning not to be used for diabetes.

  2. As it is a probabilistic model, the approach was to execute it multiple times and look at the distribution. They also tried to minimize variance: "All at the lowest randomness setting these models offer.", the post mentions. Yet the variance of the responses is surprising.

  3. A multimodal LLM should be in general able to discriminate between crema catalana and a cheese sandwich, and provide a textual, uncalculated range of how much calories the item has (internet is full with tables for calorie counting and things such as this https://fitia.app/calories-nutritional-information/cheese-sandwich-1205647).

  4. It is not clear that the "expose" surprised / outraged style is just a communication vehicle or if the author really thought that e.g. LLMs could be hypothetically able to provide confidence estimates.

> You can take it word-by-word and apply to say Javascript, and it would largely feel true - JS arguably has the worst fragmentation of any ecosystem; dozens of competing frameworks, build tools, bundlers, test runners; new frameworks constantly replacing old ones; "Javascript fatigue" is a real thing, etc., but nobody talks about "Curse of Javascript"

You also need to take into account the denominator of "number of users", though. Clojure, with a tiny population, had a cambric explosion of libraries, and now we can't argue that those are dead on one argument, and that those are "done" on the next one. There is a huge fragmentation in the clojure world, and on small populations, that hurts. Case in point: SQL libraries. Korma, yesql, hugsql, honeysql, and those are just the popular ones. Case in point: spec vs. schema vs. malli. Case in point: leiningen vs. boot vs. deps.

> I learned Lisp (once) and that opened up path to Clojure, Clojurescript, then Fennel, Janet and Clojure-Dart, libpython-clj, there's Jank that is about to break loose.

As we lispers like to say a lot, the syntax (or lack thereof) is the smallest of the issues. There is a lot of semantic difference between all of those (except libpython-clj, which does not belong to that list; but we could add Hy instead). That's even before starting to talk about library compatibility. So I'd contest whether having a common syntax is a major productivity gain.